About Me
I am a Ph.D. student in Prof. Jiawei Han’s Data Mining Group (DMG) at University of Illinois Urbana-Champaign (UIUC). I obtained my M.S. degree and B.S. degree also at UIUC, in Computer Science and Computer Engineering respectively.
I am especially passionate about developing self-supervised, unsupervised and weakly-supervised (i.e., leveraging minimal human supervision) text mining techniques for organizing and exploring text data. As such, I work at the intersection of data mining, natural language processing and applied machine learning. In the past, I have worked on text representation learning (ICLR’22, NeurIPS’21, NeurIPS’19), few-shot and zero-shot learning (ICML’23, NeurIPS’22), topic discovery (WWW’22, KDD’20, WWW’20), weakly-supervised text classification (EMNLP’20, AAAI’19, CIKM’18) and distantly-supervised named entity recognition (EMNLP’21). In the long run, my research is dedicated to mining structured knowledge from large-scale text data in label-efficient ways.
I am grateful for being supported by the Google PhD fellowship since 2021.
News
[2023.05] One paper on Weakly Supervised Scientific Text Classification has been accepted by KDD 2023!
[2023.05] Two papers on Language Model Pretraining on Text-Rich Network and Retrieval-Enhanced Weakly-Supervised Text Classification have been accepted by ACL 2023 Main Conference/Findings!
[2023.04] Our tutorial on Pretrained Language Representations for Text Understanding has been accepted by KDD 2023!
[2023.04] One paper on Few-Shot Learning has been accepted by ICML 2023!
[2023.01] Two papers on Metadata-Enhanced Scientific Text Classification and Unsupervised Online Story Discovery have been accepted by WWW 2023!
[2023.01] One paper on Learning Text-Rich Network Representations has been accepted by ICLR 2023!
[2022.12] Our tutorial on Turning Web-Scale Texts to Knowledge: Transferring Pretrained Representations to Text Mining Applications has been accepted by WWW 2023!
[2022.10] Two papers on Seed-Guided Topic Discovery and Opion Summary have been accepted by WSDM 2023!
[2022.09] One paper on Zero-Shot Language Understanding has been accepted by NeurIPS 2022!
Education
Ph.D. (Current) in Computer Science, University of Illinois Urbana-Champaign
Advisor: Prof. Jiawei HanM.S. (2019) in Computer Science, University of Illinois Urbana-Champaign
Advisor: Prof. Jiawei Han, [Thesis]B.S. (2017) in Computer Engineering, University of Illinois Urbana-Champaign
Graduated with Highest Honor & Bronze Tablet
Advisor: Prof. Sayan Mitra
Contact
Email: yumeng5[at]illinois[dot]edu
Office: Room 1113, Thomas M. Siebel Center, 201 N. Goodwin Avenue, Urbana, IL 61801